基于DSE-Net的甲状腺相关眼病患病区域轻量型分割算法

Lightweight Segmentation Algorithm for TAO Diseased Areas Based on DSE⁃Net

临床活动性评分(Clinical activity score,CAS)是临床诊断甲状腺相关眼病(Thyroid associated ophthalmopathy,TAO)的重要评估方法之一。由于TAO症状的多样性和非患病区域的影响,人工诊断TAO容易受医生的主观经验影响。精准获取TAO患者脸部关键区域是早期诊断TAO的重要前提之一。因此,本文提出了一种基于DSE-Net的TAO患病区域自动分割的轻量型算法。DSE-Net采用U-Net作为主干模型,设计的密集型挤压-激励(Dense squeeze-and-excitation,DSE)通道注意力模块逐层提取编码结构的低级特征并融合解码结构的高级特征,进一步增强模型的特征提取能力。在巩膜、眼睑和泪阜数据集上的测试证明了DSE-Net的有效性,其中Dice系数分别达到了84.8%、84.7%和92.7%,IoU分别达到了74.0%、74.7%和86.5%。同时经过大量的对比实验证明了DSE-Net的优越性。提出的模型具有参数少、结构简单和特征提取能力强等特点,为TAO的早期诊断和预后治疗提供了重要信息。

The clinical activity score(CAS)is one of the important assessment methods for clinical diagnosis of thyroid associated ophthalmopathy(TAO)disease.Manual diagnosis of TAO is susceptible to the subjective experience of ophthalmologists due to the diversity of TAO symptoms and the influence of non-diseased areas.The accurate acquisition of key facial areas of TAO patients is one of the significant prerequisites for early diagnosis of TAO.Therefore,this paper proposes a lightweight algorithm for automatic segmentation of TAO diseased areas based on DSE-Net.The DSE-Net adopts U-Net as the backbone model,and the dense squeeze-and-excitation(DSE)channel attention module,which is designed to extract low-level features of the encoding structure layer by layer and fuse high-level features of the decoding structure layer,further enhances the feature extraction capability of the model.Tests on the sclera,eyelid,and lacrimal caruncle datasets demonstrate the effectiveness of DSE-Net,with Dice coefficients reaching 84.8%,84.7%,and 92.7%,and IoUs reaching 74.0%,74.7%,and 86.5%,respectively.The superiority of DSE-Net is also proved by a large number of comparative experiments.The proposed model has fewer parameters,simple structure and strong feature extraction ability,providing significant information for the early diagnosis and prognosis treatment of TAO.